Skip to content

Commit 46a72de

Browse files
kryanbeanekryanbeane
committed
RHAIENG-2063: Add new RayCluster object and deprecate old objects
1 parent 3bad7ab commit 46a72de

20 files changed

Lines changed: 1304 additions & 80 deletions

‎demo-notebooks/additional-demos/hf_interactive.ipynb‎

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@
4040
"outputs": [],
4141
"source": [
4242
"# Import pieces from codeflare-sdk\n",
43-
"from codeflare_sdk import Cluster, ClusterConfiguration, TokenAuthentication"
43+
"from codeflare_sdk import RayCluster, TokenAuthentication"
4444
]
4545
},
4646
{
@@ -86,21 +86,20 @@
8686
"# Create our cluster and submit\n",
8787
"# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
8888
"cluster_name= \"hfgputest\"\n",
89-
"cluster = Cluster(ClusterConfiguration(\n",
89+
"cluster = RayCluster(\n",
9090
" name=cluster_name, \n",
9191
" head_memory_requests=6,\n",
9292
" head_memory_limits=8,\n",
93-
" head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
94-
" worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
93+
" head_accelerators={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_accelerators and worker_accelerators\n",
94+
" worker_accelerators={'nvidia.com/gpu':1},\n",
9595
" num_workers=1,\n",
9696
" worker_cpu_requests=8, \n",
9797
" worker_cpu_limits=8, \n",
9898
" worker_memory_requests=16, \n",
9999
" worker_memory_limits=16, \n",
100100
" # image=\"\", # Optional Field \n",
101-
" write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
102101
" # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
103-
"))"
102+
")"
104103
]
105104
},
106105
{
@@ -204,8 +203,8 @@
204203
"source": [
205204
"from codeflare_sdk import generate_cert\n",
206205
"# Create required TLS cert and export the environment variables to enable TLS\n",
207-
"generate_cert.generate_tls_cert(cluster_name, cluster.config.namespace)\n",
208-
"generate_cert.export_env(cluster_name, cluster.config.namespace)"
206+
"generate_cert.generate_tls_cert(cluster_name, cluster.namespace)\n",
207+
"generate_cert.export_env(cluster_name, cluster.namespace)"
209208
]
210209
},
211210
{

‎demo-notebooks/additional-demos/local_interactive.ipynb‎

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@
1010
"outputs": [],
1111
"source": [
1212
"# Import pieces from codeflare-sdk\n",
13-
"from codeflare_sdk import Cluster, ClusterConfiguration, TokenAuthentication"
13+
"from codeflare_sdk import RayCluster, TokenAuthentication"
1414
]
1515
},
1616
{
@@ -56,21 +56,20 @@
5656
"# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
5757
"cluster_name = \"hfgputest-1\"\n",
5858
"\n",
59-
"cluster = Cluster(ClusterConfiguration(\n",
59+
"cluster = RayCluster(\n",
6060
" name=cluster_name,\n",
6161
" head_memory_requests=6,\n",
6262
" head_memory_limits=8,\n",
63-
" head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
64-
" worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
63+
" head_accelerators={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_accelerators and worker_accelerators\n",
64+
" worker_accelerators={'nvidia.com/gpu':0},\n",
6565
" num_workers=1,\n",
6666
" worker_cpu_requests=1,\n",
6767
" worker_cpu_limits=1,\n",
6868
" worker_memory_requests=4,\n",
6969
" worker_memory_limits=6,\n",
7070
" # image=\"\", # Optional Field \n",
71-
" write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
7271
" # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
73-
"))"
72+
")"
7473
]
7574
},
7675
{
@@ -114,8 +113,8 @@
114113
"source": [
115114
"from codeflare_sdk import generate_cert\n",
116115
"\n",
117-
"generate_cert.generate_tls_cert(cluster_name, cluster.config.namespace)\n",
118-
"generate_cert.export_env(cluster_name, cluster.config.namespace)"
116+
"generate_cert.generate_tls_cert(cluster_name, cluster.namespace)\n",
117+
"generate_cert.export_env(cluster_name, cluster.namespace)"
119118
]
120119
},
121120
{

‎demo-notebooks/additional-demos/ray_job_client.ipynb‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@
1414
"outputs": [],
1515
"source": [
1616
"# Import pieces from codeflare-sdk\n",
17-
"from codeflare_sdk import Cluster, ClusterConfiguration, TokenAuthentication, RayJobClient"
17+
"from codeflare_sdk import RayCluster, TokenAuthentication, RayJobClient"
1818
]
1919
},
2020
{
@@ -57,12 +57,12 @@
5757
"source": [
5858
"# Create and configure our cluster object\n",
5959
"# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
60-
"cluster = Cluster(ClusterConfiguration(\n",
60+
"cluster = RayCluster(\n",
6161
" name='jobtest',\n",
6262
" head_memory_requests=6,\n",
6363
" head_memory_limits=8,\n",
64-
" head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
65-
" worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
64+
" head_accelerators={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_accelerators and worker_accelerators\n",
65+
" worker_accelerators={'nvidia.com/gpu':0},\n",
6666
" num_workers=2,\n",
6767
" worker_cpu_requests=1,\n",
6868
" worker_cpu_limits=1,\n",
@@ -71,7 +71,7 @@
7171
" # image=\"\", # Optional Field \n",
7272
" write_to_file=False # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
7373
" # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
74-
"))"
74+
")"
7575
]
7676
},
7777
{

‎demo-notebooks/guided-demos/1_cluster_job_client.ipynb‎

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@
1414
"outputs": [],
1515
"source": [
1616
"# Import pieces from codeflare-sdk\n",
17-
"from codeflare_sdk import Cluster, ClusterConfiguration, TokenAuthentication"
17+
"from codeflare_sdk import RayCluster, TokenAuthentication"
1818
]
1919
},
2020
{
@@ -57,23 +57,22 @@
5757
"source": [
5858
"# Create and configure our cluster object\n",
5959
"# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
60-
"cluster = Cluster(ClusterConfiguration(\n",
60+
"cluster = RayCluster(\n",
6161
" name='jobtest',\n",
6262
" head_cpu_requests=1,\n",
6363
" head_cpu_limits=1,\n",
6464
" head_memory_requests=6,\n",
6565
" head_memory_limits=8,\n",
66-
" head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
67-
" worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
66+
" head_accelerators={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_accelerators and worker_accelerators\n",
67+
" worker_accelerators={'nvidia.com/gpu':1},\n",
6868
" num_workers=2,\n",
6969
" worker_cpu_requests='250m',\n",
7070
" worker_cpu_limits=1,\n",
7171
" worker_memory_requests=4,\n",
7272
" worker_memory_limits=6,\n",
7373
" # image=\"\", # Optional Field \n",
74-
" write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
7574
" # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
76-
"))"
75+
")"
7776
]
7877
},
7978
{
@@ -229,7 +228,7 @@
229228
],
230229
"metadata": {
231230
"kernelspec": {
232-
"display_name": "Python 3",
231+
"display_name": "base",
233232
"language": "python",
234233
"name": "python3"
235234
},
@@ -243,7 +242,7 @@
243242
"name": "python",
244243
"nbconvert_exporter": "python",
245244
"pygments_lexer": "ipython3",
246-
"version": "3.9.18"
245+
"version": "3.12.7"
247246
}
248247
},
249248
"nbformat": 4,

‎demo-notebooks/guided-demos/2_basic_interactive.ipynb‎

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@
1616
"outputs": [],
1717
"source": [
1818
"# Import pieces from codeflare-sdk\n",
19-
"from codeflare_sdk import Cluster, ClusterConfiguration, TokenAuthentication"
19+
"from codeflare_sdk import RayCluster, TokenAuthentication"
2020
]
2121
},
2222
{
@@ -62,23 +62,22 @@
6262
"# Create and configure our cluster object\n",
6363
"# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
6464
"cluster_name = \"interactivetest\"\n",
65-
"cluster = Cluster(ClusterConfiguration(\n",
65+
"cluster = RayCluster(\n",
6666
" name=cluster_name,\n",
6767
" head_cpu_requests=1,\n",
6868
" head_cpu_limits=1,\n",
6969
" head_memory_requests=6,\n",
7070
" head_memory_limits=8,\n",
71-
" head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
72-
" worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
71+
" head_accelerators={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_accelerators and worker_accelerators\n",
72+
" worker_accelerators={'nvidia.com/gpu':1},\n",
7373
" num_workers=2,\n",
7474
" worker_cpu_requests='250m',\n",
7575
" worker_cpu_limits=1,\n",
7676
" worker_memory_requests=4,\n",
7777
" worker_memory_limits=6,\n",
7878
" # image=\"\", # Optional Field \n",
79-
" write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
8079
" # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
81-
"))"
80+
")"
8281
]
8382
},
8483
{
@@ -151,8 +150,8 @@
151150
"source": [
152151
"from codeflare_sdk import generate_cert\n",
153152
"# Create required TLS cert and export the environment variables to enable TLS\n",
154-
"generate_cert.generate_tls_cert(cluster_name, cluster.config.namespace)\n",
155-
"generate_cert.export_env(cluster_name, cluster.config.namespace)"
153+
"generate_cert.generate_tls_cert(cluster_name, cluster.namespace)\n",
154+
"generate_cert.export_env(cluster_name, cluster.namespace)"
156155
]
157156
},
158157
{

‎demo-notebooks/guided-demos/3_widget_example.ipynb‎

Lines changed: 5 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@
1919
"outputs": [],
2020
"source": [
2121
"# Import pieces from codeflare-sdk\n",
22-
"from codeflare_sdk import Cluster, ClusterConfiguration, TokenAuthentication, view_clusters"
22+
"from codeflare_sdk import RayCluster, TokenAuthentication, view_clusters"
2323
]
2424
},
2525
{
@@ -64,23 +64,22 @@
6464
"source": [
6565
"# Create and configure our cluster object\n",
6666
"# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
67-
"cluster = Cluster(ClusterConfiguration(\n",
67+
"cluster = RayCluster(\n",
6868
" name='widgettest',\n",
6969
" head_cpu_requests='500m',\n",
7070
" head_cpu_limits='500m',\n",
7171
" head_memory_requests=6,\n",
7272
" head_memory_limits=8,\n",
73-
" head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
74-
" worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
73+
" head_accelerators={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_accelerators and worker_accelerators\n",
74+
" worker_accelerators={'nvidia.com/gpu':0},\n",
7575
" num_workers=2,\n",
7676
" worker_cpu_requests='250m',\n",
7777
" worker_cpu_limits=1,\n",
7878
" worker_memory_requests=4,\n",
7979
" worker_memory_limits=6,\n",
8080
" # image=\"\", # Optional Field\n",
81-
" write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources\n",
8281
" # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
83-
"))"
82+
")"
8483
]
8584
},
8685
{

‎demo-notebooks/guided-demos/4_rayjob_existing_cluster.ipynb‎

Lines changed: 5 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@
3737
"metadata": {},
3838
"outputs": [],
3939
"source": [
40-
"from codeflare_sdk import Cluster, ClusterConfiguration, RayJob"
40+
"from codeflare_sdk import RayCluster, RayJob"
4141
]
4242
},
4343
{
@@ -73,21 +73,20 @@
7373
"metadata": {},
7474
"outputs": [],
7575
"source": [
76-
"cluster = Cluster(ClusterConfiguration(\n",
76+
"cluster = RayCluster(\n",
7777
" name='rayjob-cluster',\n",
7878
" head_cpu_requests=1,\n",
7979
" head_cpu_limits=1,\n",
8080
" head_memory_requests=6,\n",
8181
" head_memory_limits=8,\n",
82-
" head_extended_resource_requests={'nvidia.com/gpu':1},\n",
83-
" worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
82+
" head_accelerators={'nvidia.com/gpu':1},\n",
83+
" worker_accelerators={'nvidia.com/gpu':1},\n",
8484
" num_workers=2,\n",
8585
" worker_cpu_requests='250m',\n",
8686
" worker_cpu_limits=1,\n",
8787
" worker_memory_requests=4,\n",
8888
" worker_memory_limits=6,\n",
89-
"\n",
90-
"))\n",
89+
")\n",
9190
"\n",
9291
"cluster.apply()"
9392
]

‎demo-notebooks/guided-demos/5_submit_rayjob_cr.ipynb‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@
2929
"metadata": {},
3030
"outputs": [],
3131
"source": [
32-
"from codeflare_sdk import RayJob, ManagedClusterConfig"
32+
"from codeflare_sdk import RayJob, RayCluster"
3333
]
3434
},
3535
{
@@ -55,7 +55,7 @@
5555
"id": "5581eca9",
5656
"metadata": {},
5757
"source": [
58-
"Next we'll need to define the ManagedClusterConfig. Kuberay will use this to spin up a short-lived RayCluster that will only exist as long as the job"
58+
"Next we'll need to define the RayCluster configuration. Kuberay will use this to spin up a short-lived RayCluster that will only exist as long as the job"
5959
]
6060
},
6161
{
@@ -65,7 +65,7 @@
6565
"metadata": {},
6666
"outputs": [],
6767
"source": [
68-
"cluster_config = ManagedClusterConfig(\n",
68+
"cluster_config = RayCluster(\n",
6969
" head_memory_requests=6,\n",
7070
" head_memory_limits=8,\n",
7171
" num_workers=2,\n",
@@ -83,7 +83,7 @@
8383
"id": "02a2b32b",
8484
"metadata": {},
8585
"source": [
86-
"Lastly we can pass the ManagedClusterConfig into the RayJob and submit it. You do not need to worry about tearing down the cluster when the job has completed, that is handled for you!"
86+
"Lastly we can pass the RayCluster configuration into the RayJob and submit it. You do not need to worry about tearing down the cluster when the job has completed, that is handled for you!"
8787
]
8888
},
8989
{

‎pyproject.toml‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -41,6 +41,7 @@ kubernetes = ">= 27.2.0"
4141
cryptography = "43.0.3"
4242
executing = "1.2.0"
4343
pydantic = ">= 2.10.6"
44+
typing_extensions = ">= 4.12.0"
4445
ipywidgets = "8.1.2"
4546

4647
[[tool.poetry.source]]

‎src/codeflare_sdk/__init__.py‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,10 @@
11
from .ray import (
22
Cluster,
33
ClusterConfiguration,
4+
RayCluster,
5+
RayClusterInfo,
46
RayClusterStatus,
57
CodeFlareClusterStatus,
6-
RayCluster,
78
get_cluster,
89
list_all_queued,
910
list_all_clusters,

0 commit comments

Comments
 (0)